llama.cpp
3fec68be - convert : add support of codeqwen due to tokenizer (#6707)

Commit

1 year ago

convert : add support of codeqwen due to tokenizer (#6707) * add support of codeqwen due to tokenizer * override load_hparams * fix typo * fix load_params * convert : fix whitespace --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

References

#6707 - add support of codeqwen due to tokenizer

Author

JustinLin610

Parents

c8297c6a

Files1

convert-hf-to-gguf.py

llama.cpp 3fec68be - convert : add support of codeqwen due to tokenizer (#6707)

llama.cpp
3fec68be - convert : add support of codeqwen due to tokenizer (#6707)